Bruno Pedro's public notes

Found at “All the Hard Stuff Nobody Talks About when Building Products with LLMs | Honeycomb” on 2023-05-29 11:05:37 +02:00.

Unfortunately, accepting broad inputs and needing to apply some form of “best practice” on outputs really throws a wrench into prompt engineering efforts. We find that if we experiment with one approach, it improves outputs at the cost of accepting less broad inputs, or vice-versa. There’s a lot more work we can do to improve our prompting, but there’s no apparent playbook we can just use right now.